Lime and fertilizer recommendation system for coconut trees

Fertilizer recommendation to most agricultural crops is based on response curves. Such curves are constructed from field experimental data, obtained for a particular condition and may not be reliable to be applied to other regions. The aim of this study was to develop a Lime and Fertilizer Recommendation System for Coconut Crop based on the nutritional balance. The System considers the expected productivity and plant nutrient use efficiency to estimate nutrient demand, and effective rooting layer, soil nutrient availability, as well as any other nutrient input to estimate the nutrient supply. Comparing the nutrient demand with the nutrient supply the System defines the nutrient balance. If the balance for a given nutrient is negative, lime and, or, fertilization is recommended. On the other hand, if the balance is positive, no lime or fertilizer is needed. For coconut trees, the fertilization regime is divided in three stages: fertilization at the planting spot, band fertilization and fertilization at the production phase. The data set for the development of the System for coconut trees was obtained from the literature. The recommendations generated by the System were compared to those derived from recommendation tables used for coconut crop in Brazil. The main differences between the two procedures were for the P rate applied in the planting hole, which was higher in the proposed System because the tables do not pay heed to the pit volume, whereas the N and K rates were lower. The crop demand for K is very high, and the rates recommended by the System are superior to the table recommendations for the formation and initial production stage. The fertilizer recommendations by the System are higher for the phase of coconut tree growth as compared to the production phase, because greater amount of biomass is produced in the first phase.

Intelligent recommendation system for e-learning platforms

As more and more digital resources are available, finding the appropriate document becomes harder. Thus, a new kind of tools, able to recommend the more appropriated resources according the user needs, becomes even more necessary. The current project implements an intelligent recommendation system for elearning platforms. The recommendations are based on one hand, the performance of the user during the training process and on the other hand, the requests made by the user in the form of search queries. All information necessary for decision-making process of recommendation will be represented in the user model. This model will be updated throughout the target user interaction with the platform.

A clinical recommendation system to maternity care

Nowadays in healthcare, the Clinical Decision Support Systems are used in order to help health professionals to take an evidence-based decision. An example is the Clinical Recommendation Systems. In this sense, it was developed and implemented in Centro Hospitalar do Porto a pre-triage system in order to group the patients on two levels (urgent or outpatient). However, although this system is calibrated and specific to the urgency of obstetrics and gynaecology, it does not meet all clinical requirements by the general department of the Portuguese HealthCare (Direção Geral de Saúde). The main requirement is the need of having priority triage system characterized by five levels. Thus some studies have been conducted with the aim of presenting a methodology able to evolve the pre-triage system on a Clinical Recommendation System with five levels. After some tests (using data mining and simulation techniques), it has been validated the possibility of transformation the pre-triage system in a Clinical Recommendation System in the obstetric context. This paper presents an overview of the Clinical Recommendation System for obstetric triage, the model developed and the main results achieved.

FERTILIZER RECOMMENDATION SYSTEM FOR MELON BASED ON NUTRITIONAL BALANCE

Melon is one of the most demanding cucurbits regarding fertilization, requiring knowledge of soils, crop nutritional requirements, time of application, and nutrient use efficiency for proper fertilization. Developing support systems for decision-making for fertilization that considers these variables in nutrient requirement and supply is necessary. The objective of this study was parameterization of a fertilizer recommendation system for melon (Ferticalc-melon) based on nutritional balance. To estimate fertilizer recommendation, the system considers the requirement subsystem (REQ), which includes the demand for nutrients by the plant, and the supply subsystem (SUP), which corresponds to the supply of nutrients through the soil and irrigation water. After determining the REQtotal and SUPtotal, the system calculates the nutrient balances for N, P, K, Ca, Mg, and S, recommending fertilizer application if the balance is negative (SUP < REQ), but not if the balance is positive or zero (SUP ≥ REQ). Simulations were made for different melon types (Yellow, Cantaloupe, Galia and Piel-de-sapo), with expected yield of 45 t ha-1. The system estimated that Galia type was the least demanding in P, while Piel-de-sapo was the most demanding. Cantaloupe was the least demanding for N and Ca, while the Yellow type required less K, Mg, and S. As compared to other fertilizer recommendation methods adopted in Brazil, the Ferticalc system was more dynamic and flexible. Although the system has shown satisfactory results, it needs to be evaluated under field conditions to improve its recommendations.

MLTDL - Recommendation system for Digital Libraries

Presentation at Open Repositories 2014, Helsinki, Finland, June 9-13, 2014

The Audiomomma Music Recommendation System

We design and implement a system that recommends musicians to listeners. The basic idea is to keep track of what artists a user listens to, to find other users with similar tastes, and to recommend other artists that these similar listeners enjoy. The system utilizes a client-server architecture, a web-based interface, and an SQL database to store and process information. We describe Audiomomma-0.3, a proof-of-concept implementation of the above ideas.

Progettazione ed implementazione di un recommendation system di articoli scientifici basato su Apache Mahout

Il focus di questo elaborato è sui sistemi di recommendations e le relative caratteristiche. L'utilizzo di questi meccanism è sempre più forte e presente nel mondo del web, con un parallelo sviluppo di soluzioni sempre più accurate ed efficienti. Tra tutti gli approcci esistenti, si è deciso di prendere in esame quello affrontato in Apache Mahout. Questa libreria open source implementa il collaborative-filtering, basando il processo di recommendation sulle preferenze espresse dagli utenti riguardo ifferenti oggetti. Grazie ad Apache Mahout e ai principi base delle varie tipologie di recommendationè stato possibile realizzare un applicativo web che permette di produrre delle recommendations nell'ambito delle pubblicazioni scientifiche, selezionando quegli articoli che hanno un maggiore similarità con quelli pubblicati dall'utente corrente. La realizzazione di questo progetto ha portato alla definizione di un sistema ibrido. Infatti l'approccio alla recommendation di Apache Mahout non è completamente adattabile a questa situazione, per questo motivo le sue componenti sono state estese e modellate per il caso di studio. Siè cercato quindi di combinare il collaborative filtering e il content-based in un unico approccio. Di Apache Mahout si è mantenuto l'algoritmo attraverso il quale esaminare i dati del data set, tralasciando completamente l'aspetto legato alle preferenze degli utenti, poichè essi non esprimono delle valutazioni sugli articoli. Del content-based si è utilizzata l'idea del confronto tra i titoli delle pubblicazioni. La valutazione di questo applicativo ha portato alla luce diversi limiti, ma anche possibili sviluppi futuri che potrebbero migliorare la qualità delle recommendations, ma soprattuto le prestazioni. Grazie per esempio ad Apache Hadoop sarebbe possibile una computazione distribuita che permetterebbe di elaborare migliaia di dati con dei risultati più che discreti.

Collaborative filtering and deep learning based recommendation system for cold start items

Recommender system is a specific type of intelligent systems, which exploits historical user ratings on items and/or auxiliary information to make recommendations on items to the users. It plays a critical role in a wide range of online shopping, e-commercial services and social networking applications. Collaborative filtering (CF) is the most popular approaches used for recommender systems, but it suffers from complete cold start (CCS) problem where no rating record are available and incomplete cold start (ICS) problem where only a small number of rating records are available for some new items or users in the system. In this paper, we propose two recommendation models to solve the CCS and ICS problems for new items, which are based on a framework of tightly coupled CF approach and deep learning neural network. A specific deep neural network SADE is used to extract the content features of the items. The state of the art CF model, timeSVD++, which models and utilizes temporal dynamics of user preferences and item features, is modified to take the content features into prediction of ratings for cold start items. Extensive experiments on a large Netflix rating dataset of movies are performed, which show that our proposed recommendation models largely outperform the baseline models for rating prediction of cold start items. The two proposed recommendation models are also evaluated and compared on ICS items, and a flexible scheme of model retraining and switching is proposed to deal with the transition of items from cold start to non-cold start status. The experiment results on Netflix movie recommendation show the tight coupling of CF approach and deep learning neural network is feasible and very effective for cold start item recommendation. The design is general and can be applied to many other recommender systems for online shopping and social networking applications. The solution of cold start item problem can largely improve user experience and trust of recommender systems, and effectively promote cold start items.

Establishing Standards for the Integrated Recommendation and Diagnosis System (DRIS) for Irrigated Bean Crops

This article addresses the establishment of integrated diagnostics and recommendation system (DRIS) standards for irrigated bean crops (Phaseolus vulgaris) and compares leaf concentrations and productivity in low- and high-productivity populations. The work was carried out in Santa Fe de Goias, Goias State, Brazil, in the agricultural years 1999/2000 and 2000/2001. For the nutritional diagnosis, leaf samples were collected, and leaf concentrations of nitrogen (N), phosphorus (P), potassium (K), calcium (Ca), magnesium (Mg), sulfur (S), boron (B), copper (Cu), iron (Fe), manganese (Mn), and zinc (Zn) were established in 100 commercial bean crops. A database was set up listing the leaf nutrient content and the respective productivities, subdivided into two subpopulations, high and low productivity, using a bean yield value of 3000 kg ha-1 to separate these subpopulations. Sufficiency values found in the high-productivity population matched only for the micronutrients B and Zn. The nutritional balance among the populations studied was coherent and was lower in the high-productivity population. The DRIS standards proposed for irrigated bean farming were efficient in evaluating the nutritional status of the crop areas studied. Calcium, Cu, and S were found to be the least available nutrients, indicating high response potential for the fertilizing using these nutrients.

'Movie Recommendation Systems Using An Artificial Immune System'

We apply the Artificial Immune System (AIS)technology to the collaborative Filtering (CF)technology when we build the movie recommendation system. Two different affinity measure algorithms of AIS, Kendall tau and Weighted Kappa, are used to calculate the correlation coefficients for this movie recommendation system. From the testing we think that Weighted Kappa is more suitable than Kendall tau for movie problems.

'Movie Recommendation Systems Using An Artificial Immune System'

We apply the Artificial Immune System (AIS)technology to the collaborative Filtering (CF)technology when we build the movie recommendation system. Two different affinity measure algorithms of AIS, Kendall tau and Weighted Kappa, are used to calculate the correlation coefficients for this movie recommendation system. From the testing we think that Weighted Kappa is more suitable than Kendall tau for movie problems.

Recommendation and planning through mobile devices in tourism context

In this paper we present a mobile recommendation and planning system, named PSiS Mobile. It is designed to provide effective support during a tourist visit through context-aware information and recommendations about points of interest, exploiting tourist preferences and context. Designing a tool like this brings several challenges that must be addressed. We discuss how these challenges have been overcame, present the overall system architecture, since this mobile application extends the PSiS project website, and the mobile application architecture.

NUTRIENT RECOMMENDATION MODEL FOR CARROT CROP – FERTICALC CARROT

ABSTRACT The literature on fertilization for carrot growing usually recommends nutrient application rates for yield expectations lower than the yields currently obtained. Moreover, the recommendation only considers the results of soil chemical analysis and does not include effects such as crop residues or variations in yield levels. The aim of this study was to propose a fertilizer recommendation system for carrot cultivation (FERTICALC Carrot) which includes consideration of the nutrient supply by crop residues, variation in intended yield, soil chemical properties, and the growing season (winter or summer). To obtain the data necessary for modeling nutritional requirements, 210 carrot production stands were sampled in the region of Alto Paranaíba, State of Minas Gerais, Brazil. The dry matter content of the roots, the coefficient of biological utilization of nutrients in the roots, and the nutrient harvest index for summer and winter crops were determined for these samples. To model the nutrient supply by the soil, the literature was surveyed in regard to this theme. A modeling system was developed for recommendation of macronutrients and B. For cationic micronutrients, the system only reports crop nutrient export and extraction. The FERTICALC which was developed proved to be efficient for fertilizer recommendation for carrot cultivation. Advantages in relation to official fertilizer recommendation tables are continuous variation of nutrient application rates in accordance with soil properties and in accordance with data regarding the extraction efficiency of modern, higher yielding cultivars.

Analisi dei comportamenti degli utenti per lo sviluppo di un sistema di App Recommendation

Negli ultimi cinque anni lo sviluppo di applicazioni mobile ha visto un grandissimo incremento dovuto pricipalmente all’esplosione della diffusione di smartphone; questo fenomeno ha reso disponibile agli analisti una enorme quantità di dati sulle abitudini degli utenti. L’approccio centralizzato nella distribuzione delle applicazioni da parte dei grandi provider quali Apple, Google e Microsoft ha permesso a migliaia di sviluppatori di tutto il mondo di raggiungere con i loro prodotti gli utenti finali e diffondere l’utilizzo di applicativi installabili; le app infatti sono diventate in poco tempo fondamentali nella vita di tutti i giorni e in alcuni casi hanno sostituito funzioni primarie del telefono cellulare. Obiettivo principale di questo studio sarà inferire pattern comportamentali dall’analisi di una grossa mole di dati riguardanti l’utilizzo dello smartphone e delle app installabili da parte di un gruppo di utenti. Ipotizzando di avere a disposizione tutte le azioni che un determinato bacino di utenza effettua nella selezione delle applicazioni di loro interesse quando accedono al marketplace (luogo digitale da cui è possibile scaricare nuove applicazioni ed installarle) è possibile stimare, ovviamente con un certo margine di errore, dati sensibili dell’utente quali: Sesso, Età, Interessi e così via analizzandoli in relazione ad un modello costruito su dati di un campione di utenti ben noto. Costruiremo così un modello utilizzando dati di utenti ben noti di cui conosciamo i dettagli sensibili e poi, tramite avanzate tecniche di regressione e classificazione saremo in grado di definire se esiste o meno una correlazione tra le azioni effettuate su uno Smartphone e il profilo dell’utente. La seconda parte della tesi sarà incentrata sull'analisi di sistemi di raccomandazioni attualmente operativi e ci concentreremo sullo studio di possibili sviluppi sviluppi futuri di questi sistemi partendo dai risultati sperimentali ottenuti.

Social Recommendation Based on Content and Trust

Report published in the Proceedings of the National Conference on "Education and Research in the Information Society", Plovdiv, May, 2014